保存到文件乱码和没有那么条数据

Question

问题遇到的现象和发生背景

原地址：https://mp.weixin.qq.com/s/54dcJO2KR9aMTQJh5OlSzg
爬取数据控制台没有出问题 可是爬取到文件就出问题

问题相关代码，请勿粘贴截图

import requests
import requests
import csv
import time
import json
import requests
from lxml import etree
from pymongo import MongoClient
from bs4 import BeautifulSoup
import pandas as pd

def getOnepage(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36',
        'Cookie': 'bid=NX8M2NI7rfg; douban-fav-remind=1; __yadk_uid=TEJSv3vlFpxrnShgBGXWW51qExiqLCiD; __gads=ID=35ed214a9a0f04f3-229b40ae8cc5003e:T=1609826897:RT=1609826897:S=ALNI_MbjrOjiMxJC6bra_BWqa1z6LwJvFA; ll="118267"; viewed="1007305"; gr_user_id=38f71f7e-49a3-4463-a3e9-dd3f77625dad; _ga=GA1.2.1355032985.1609826898; _vwo_uuid_v2=D6A8A09C6232AC6A436C3775284DBE348|dadd79d0f01552308d196454329600a7; dbcl2="247324733:YcdnDsCblB0"; push_noty_num=0; push_doumail_num=0; __utmv=30149280.24732; ck=MMTN; _pk_ref.100001.8cb4=%5B%22%22%2C%22%22%2C1637395735%2C%22https%3A%2F%2Fwww.gameres.com%2F%22%5D; _pk_ses.100001.8cb4=*; __utma=30149280.1355032985.1609826898.1637309781.1637395736.17; __utmc=30149280; __utmz=30149280.1637395736.17.14.utmcsr=gameres.com|utmccn=(referral)|utmcmd=referral|utmcct=/; __utmt=1; _pk_id.100001.8cb4=b87f2f239f7dd7c8.1609826897.15.1637395743.1637309781.; __utmb=30149280.4.10.1637395736'

    }
    # 发送请求,得到响应

    response = requests.get(url, headers=headers)
    return response.json()  # 文本

# 解析一页的数据
def parseOnepage (res):


    col = ['name', 'star', 'rating', 'platforms', 'n_ratings', 'genres', 'content']

    n = len(res['games'])
    list1=[]
    for j in range(n):
        item={}
        item['name'] = res['games'][j]['title']
        item['star'] = res['games'][j]['star']
        item['rating'] = res['games'][j]['rating']
        item['platforms'] = res['games'][j]['platforms']
        item['n_ratings'] = res['games'][j]['n_ratings']
        item['genres'] = res['games'][j]['genres']
        item['content'] = res['games'][j]['review']['content']
        print(item)
        list1.append(item)
    return list1
def savaData(item):
    with open('douban.csv', 'w', newline='', encoding='utf-8')as f:
        fieldnames = ['name', 'star', 'rating', 'platforms', 'n_ratings',
                      'genres','content']
        write = csv.DictWriter(f, fieldnames=fieldnames)
        write.writeheader()
        write.writerows(item)
def main():
    for i in range(1,100):
        url="https://www.douban.com/j/ilmen/game/search?genres=&platforms=&q=&sort=rating&more="+str(i)
        response = getOnepage(url)
        # parseOnepage(response)
        savaData(parseOnepage(response))
if __name__ == '__main__': # 程序的窗口
    main()

运行结果及报错内容

我的解答思路和尝试过的方法

我想要达到的结果

Answer 1

你这是爬取了多少个页面呀,我跑了好久,记得采纳
修改了你数据提取后的多余回车和乱码现象,还有提取的数据有些字符是异形字符,如果你想要显示,建议换种方法存数据,修改了存文件的函数,具体哪些地方你再看看

import requests


def getOnepage(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36',
        'Cookie': 'bid=NX8M2NI7rfg; douban-fav-remind=1; __yadk_uid=TEJSv3vlFpxrnShgBGXWW51qExiqLCiD; __gads=ID=35ed214a9a0f04f3-229b40ae8cc5003e:T=1609826897:RT=1609826897:S=ALNI_MbjrOjiMxJC6bra_BWqa1z6LwJvFA; ll="118267"; viewed="1007305"; gr_user_id=38f71f7e-49a3-4463-a3e9-dd3f77625dad; _ga=GA1.2.1355032985.1609826898; _vwo_uuid_v2=D6A8A09C6232AC6A436C3775284DBE348|dadd79d0f01552308d196454329600a7; dbcl2="247324733:YcdnDsCblB0"; push_noty_num=0; push_doumail_num=0; __utmv=30149280.24732; ck=MMTN; _pk_ref.100001.8cb4=%5B%22%22%2C%22%22%2C1637395735%2C%22https%3A%2F%2Fwww.gameres.com%2F%22%5D; _pk_ses.100001.8cb4=*; __utma=30149280.1355032985.1609826898.1637309781.1637395736.17; __utmc=30149280; __utmz=30149280.1637395736.17.14.utmcsr=gameres.com|utmccn=(referral)|utmcmd=referral|utmcct=/; __utmt=1; _pk_id.100001.8cb4=b87f2f239f7dd7c8.1609826897.15.1637395743.1637309781.; __utmb=30149280.4.10.1637395736'
    }
    # 发送请求,得到响应
    response = requests.get(url, headers=headers)
    return response.json()  # 文本


# 解析一页的数据
def parseOnepage(res):
    col = ['name', 'star', 'rating', 'platforms', 'n_ratings', 'genres', 'content']
    n = len(res['games'])
    list1 = []
    for j in range(n):
        item = {}
        item['name'] = res['games'][j]['title'].replace('\r\n', '')
        item['star'] = res['games'][j]['star'].replace('\r\n', '')
        item['rating'] = res['games'][j]['rating'].replace('\r\n', '')
        item['platforms'] = res['games'][j]['platforms'].replace('\r\n', '')
        item['n_ratings'] = str(res['games'][j]['n_ratings'])
        item['genres'] = res['games'][j]['genres'].replace('\r\n', '')
        item['content'] = res['games'][j]['review']['content'].replace('\r\n', '')
        list1.append(item)
    return list1


def savaData(item):
    import os
    if os.path.exists('douban.csv'):
        with open('douban.csv', 'a+') as f:
            for i in item:
                c = list(i.values())
                b = ','.join(c)
                try:
                    f.writelines(b + '\n')
                except:
                    pass
    else:
        with open('douban.csv', 'w+') as f:
            title = "name, star, rating, platforms, n_ratings,genres, content\n"
            f.writelines(title)
            for i in item:
                c = list(i.values())
                b = ','.join(c)
                try:
                    f.writelines(b + '\n')
                except:
                    pass

        # write = csv.DictWriter(f, fieldnames=fieldnames)
        # write.writeheader()
        # write.writerows(item)


def main():
    for i in range(1, 100):
        url = "https://www.douban.com/j/ilmen/game/search?genres=&platforms=&q=&sort=rating&more=" + str(i)
        response = getOnepage(url)
        # parseOnepage(response)
        savaData(parseOnepage(response))


if __name__ == '__main__':  # 程序的窗口
    main()